聚类分析在肺结节识别中的应用

doi:10.11772/j.issn.1001-9081.2014.07.2050

计算机应用 ›› 2014, Vol. 34 ›› Issue (7): 2050-2053.DOI: 10.11772/j.issn.1001-9081.2014.07.2050

聚类分析在肺结节识别中的应用

孙娟¹,王兵¹,杨颖²,田学东¹

1. 河北大学数学与计算机学院，河北保定 071002;
2. 河北大学附属医院 CT室，河北保定 071000

收稿日期:2014-01-16 修回日期:2014-03-07 出版日期:2014-07-01 发布日期:2014-08-01
通讯作者: 王兵
作者简介:孙娟(1975-)，女，河北保定人，讲师，硕士，主要研究方向:机器学习、图像处理；王兵(1966-)，女，河北承德人，教授，主要研究方向:图像处理模式识别；杨颖(1970-)，女，河北保定人，硕士，主要研究方向:医学影像;田学东(1963-),男,河北保定人，教授,博士, 主要研究方向:模式识别与图像处理、中文信息处理。
基金资助:
河北省自然科学基金资助项目;河北省自然科学基金资助项目

Research on cluster analysis in pulmonary nodule recognition

SUN Juan¹,WANG Bing¹,YANG Ying²,TIAN Xuedong¹

1. College of Mathematics and Computer Science, Hebei University, Baoding Hebei 071002,China;
2. CT Department, Hebei University Affiliated Hospital, Baoding Hebei 071000,China

Received:2014-01-16 Revised:2014-03-07 Online:2014-07-01 Published:2014-08-01
Contact: WANG Bing

摘要/Abstract

摘要：

针对肺部微小结节难于识别的问题，提出用聚类算法分析肺部感兴趣区域(ROI)的方法。为进一步提高运行速度和识别率，提出全权模糊聚类算法PWFCM，给每个样本及其特征分别赋予权值并引入新的隶属度约束改进收敛性；利用二次聚类策略降低不均衡ROI数据造成的低敏感度。对实际CT影像数据进行测试，实验结果表明：该聚类分析具有高敏感度和低假阳性率，能有效地检测出肺结节。

Abstract:

Aiming at the problem of pulmonary small nodules was difficult to identify, a method using fuzzy C-means clustering algorithm to analyse the lung Region Of Interest (ROI) was presented. An improved Fuzzy C-Means clustering algorithm based on Plurality of Weight (PWFCM) was presented to enhance the accurate rate and speed of small nodules recognition. To improve the convergence, each sample and its features were weighted and a new membership constraint was introduced. The low sensitivity from the uneven ROI data was decreased by using a double clustering strategy. The experimental results tested on the real CT image data show that PWFCM algorithm can detect lung nodules with a higher sensitivity and lower false positive rate.

孙娟王兵杨颖田学东. 聚类分析在肺结节识别中的应用[J]. 计算机应用, 2014, 34(7): 2050-2053.

SUN Juan WANG Bing YANG Ying TIAN Xuedong. Research on cluster analysis in pulmonary nodule recognition[J]. Journal of Computer Applications, 2014, 34(7): 2050-2053.

参考文献

［1］NIE S, SUN X,CHEN Z. Progress in computer-aided detection for pulmonary nodule using CT image［J］.Chinese Journal of Medical Physics,2009,26(2):1075-1079.(聂生东,孙希文,陈兆学.基于CT图像的肺结节计算机辅助检测技术的研究进展［J］.中国医学物理学杂志,2009,26(2):1075-1079.)
［2］MICHELA A, MARCO C, BEATRICE L, et al. Computer-aided detection of lung nodules based on decision fusion techniques［J］.Industrial and Commercial Application,2011,14(1):295-310.
［3］WEI Y, GUO W, SUN Y,et al. Feature selection and classification algorithm for region of interest in lung cancer CAD system［J］. Information and Control, 2008,12(4): 445-451.(魏颖,郭薇,孙月芳,等.面向肺癌CAD系统的感兴趣区域特征选择与分类算法［J］.信息与控制,2008,12(4):445-451.)
［4］WEI Y,LI R,YANG J, et al. An algorithm for segmentation of lung ROI by mean-shift clustering combined with multi-scale HESSIAN matrix dot filtering ［J］.Journal of Central South University, 2012,19(12):3500-3509.
［5］GUO W, WEI Y, ZHOU H, et al. Adaptive detection algorithm for pulmonary nodules ［J］.Journal of System Simulation, 2009,21(13): 3955-3958.(郭薇,魏颖,周翰逊,等.肺结节的自适应检测算法［J］.系统仿真学报,2009,21(13): 3955-3958.)
［6］HE Z,LIANG Y,HUANG X,et al. Research on the feature extraction approach for SPNs detection［J］.Journal of Chinese Computer Systems, 2009, 30(10):2074-2077.(何中市，梁琰，黄学全，等.肺结节检测中特征提取方法研究［J］.小型微型计算机系统,2009, 30(10):2074-2077.)
［7］WANG L, LI B,TIAN L,et al. Intelligent detection of lung nodules based on rules and multi-feature tracking［J］.Journal of Biomedical Engineering Research, 2010, 29(2):79-83,203.(王立非，李彬，田联房,等.基于规则及多特征跟踪的肺结节的智能检测方法［J］.生物医学工程研究,2010, 29(2):79-83,203.)
［8］WU Y,YANG X,XU M. et al. Graph cuts medical image segmentation algorithm based on K-means clustering［J］.Computer Engineering, 2011，37(5)：232-234.(吴永芳，杨鑫，徐敏,等.基于K均值聚类的图割医学图像分割算法［J］.计算机工程，2011，37(5)：232-234.)
［9］SUN X,TIAN Q, LI L,et al.Computer-aided detection algorithm for pulmonary nodule based on the improved fuzzy c-means cluster algorithm［J］.Progress in Modern Biomedicine, 2010,10(17):3326-3331.(孙旭辉,田启川,李临生，等.基于改进的模糊C均值聚类的肺结节计算机辅助诊断算法研究［J］.现代生物医学进展,2010,10(17):3326-3331.)
［10］ALFONSO C, CARMEN B, ALBERTO R, et al. An analysis of different clustering algorithms for ROI detection in high resolutions CT lung images［C］// Proceedings of the 2010 International Conference on Computer Vision and Graphics. Berlin: Springer, 2010: 241-248.
［11］CHEN K,LI B,TIAN L. Pulmonary nodules detection algorithm based on local threshold and iterative of clustering center［J］.Computer Science, 2012，39(2)：302-304.(陈侃,李彬,田联房.基于局部阈值和聚类中心迭代的肺结节检测算法［J］.计算机科学，2012，39(2)：302-304.)
［12］ZHANG J,DUAN F. Improved k-means algorithm with meliorated initial centers［J］.Computer Engineering and Design,2013,34(5): 1691-1694,1699.(张靖,段富.优化初始聚类中心的改进k-means算法［J］. 计算机工程与设计,2013,34(5): 1691-1694,1699.)
［13］ZHU L, WANG S, DENG Z.Research on generalized fuzzy c-means clustering algorithm with improved fuzzy partitions［J］.Journal of Computer Research and Development, 2009,46(5):814-822.(朱林,王士同,邓赵红.改进模糊划分的FCM聚类算法的一般化研究［J］.计算机研究与发展,2009,46(5):814-822.)
［14］ZHANG R, ZHANG J. Fuzzy clustering algorithm based on w-mean distance［J］.Journal of Computer Applications, 2012，32(7):1978 -1982,1986.(张瑞丽，张继福.基于w-距离均值的模糊聚类算法［J］.计算机应用，2012，32(7):1978 -1982,1986.)

聚类分析在肺结节识别中的应用

Research on cluster analysis in pulmonary nodule recognition

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics